Blog Tags GitHub

streaming-inference

2 posts tagged with "streaming-inference"

MiniWorld: Democratizing the Training of Video World Models from Scratch

MiniWorld 提出轻量级可复现的视频世界模型训练框架，基于块因果 Video DiT + Flow Matching + 块级非递减噪声调度 + 滚动 KV Cache 流水线异步去噪，可在单台 8-GPU 服务器上数天内完成训练

video-world-model diffusion-transformer flow-matching block-causal-attention streaming-inference embodied-ai diffusion-forcing kv-cache

ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference

通过阶段式协调推理架构，实现流式 VideoLLM 在单 A100 GPU 上达到 134 FPS 吞吐量和低于 50ms TTFT

video-understanding videollm streaming-inference token-dropping inference-optimization real-time-processing